Publicação

Transfer learning with audioSet to voice pathologies identification in continuous speech

Detalhes bibliográficos
Resumo:	The classification of pathological diseases with the implementation of concepts of Deep Learning has been increasing considerably in recent times. Among the works developed there are good results for the classification in sustained speech with vowels, but few related works for the classification in continuous speech. This work uses the German Saarbrücken Voice Database with the phrase “Guten Morgen, wie geht es Ihnen?” to classify four classes: dysphonia, laryngitis, paralysis of vocal cords and healthy voices. Transfer learning concepts were used with the AudioSet database. Two models were developed based on Long-Short-Term-Memory and Convolutional Network for classification of extracted embeddings and comparison of the best results, using cross-validation. The final results allowed to obtaining 40% of f1-score for the four classes, 66% f1-score for Dysphonia x Healthy, 67% for Laryngitis x healthy and 80% for Paralysis x Healthy.
Autores principais:	Guedes, Victor
Outros Autores:	Teixeira, Felipe; Oliveira, Alessa Anjos de; Fernandes, Joana Filipa Teixeira; Silva, Letícia; Candido Junior, Arnaldo; Teixeira, João Paulo
Assunto:	Long short term memory Convolutional neural network SVD Deep learning Voice pathologies diagnose
Ano:	2019
País:	Portugal
Tipo de documento:	comunicação em conferência
Tipo de acesso:	acesso aberto
Instituição associada:	Instituto Politécnico de Bragança
Idioma:	inglês
Origem:	Biblioteca Digital do IPB

Descrição
Resumo:	The classification of pathological diseases with the implementation of concepts of Deep Learning has been increasing considerably in recent times. Among the works developed there are good results for the classification in sustained speech with vowels, but few related works for the classification in continuous speech. This work uses the German Saarbrücken Voice Database with the phrase “Guten Morgen, wie geht es Ihnen?” to classify four classes: dysphonia, laryngitis, paralysis of vocal cords and healthy voices. Transfer learning concepts were used with the AudioSet database. Two models were developed based on Long-Short-Term-Memory and Convolutional Network for classification of extracted embeddings and comparison of the best results, using cross-validation. The final results allowed to obtaining 40% of f1-score for the four classes, 66% f1-score for Dysphonia x Healthy, 67% for Laryngitis x healthy and 80% for Paralysis x Healthy.